| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 104, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 1.317004218697548, |
| "epoch": 0.009685230024213076, |
| "grad_norm": 1.2896121740341187, |
| "learning_rate": 0.0, |
| "loss": 2.082634687423706, |
| "mean_token_accuracy": 0.5258517861366272, |
| "num_tokens": 97328.0, |
| "step": 1 |
| }, |
| { |
| "entropy": 1.306379646062851, |
| "epoch": 0.01937046004842615, |
| "grad_norm": 1.2239129543304443, |
| "learning_rate": 3.125e-06, |
| "loss": 2.047252655029297, |
| "mean_token_accuracy": 0.5331005752086639, |
| "num_tokens": 194259.0, |
| "step": 2 |
| }, |
| { |
| "entropy": 1.3193936496973038, |
| "epoch": 0.029055690072639227, |
| "grad_norm": 1.1433645486831665, |
| "learning_rate": 6.25e-06, |
| "loss": 2.0007200241088867, |
| "mean_token_accuracy": 0.5382249727845192, |
| "num_tokens": 291639.0, |
| "step": 3 |
| }, |
| { |
| "entropy": 1.421342894434929, |
| "epoch": 0.0387409200968523, |
| "grad_norm": 0.997297465801239, |
| "learning_rate": 9.375000000000001e-06, |
| "loss": 1.9897820949554443, |
| "mean_token_accuracy": 0.5354432910680771, |
| "num_tokens": 389132.0, |
| "step": 4 |
| }, |
| { |
| "entropy": 1.493358463048935, |
| "epoch": 0.048426150121065374, |
| "grad_norm": 0.7811200022697449, |
| "learning_rate": 1.25e-05, |
| "loss": 1.9146728515625, |
| "mean_token_accuracy": 0.5432016626000404, |
| "num_tokens": 487010.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 1.6673749834299088, |
| "epoch": 0.05811138014527845, |
| "grad_norm": 0.5001599192619324, |
| "learning_rate": 1.5625e-05, |
| "loss": 1.8388503789901733, |
| "mean_token_accuracy": 0.5485250800848007, |
| "num_tokens": 584854.0, |
| "step": 6 |
| }, |
| { |
| "entropy": 1.8042271435260773, |
| "epoch": 0.06779661016949153, |
| "grad_norm": 0.4208337068557739, |
| "learning_rate": 1.8750000000000002e-05, |
| "loss": 1.825950026512146, |
| "mean_token_accuracy": 0.5503732189536095, |
| "num_tokens": 681659.0, |
| "step": 7 |
| }, |
| { |
| "entropy": 1.9454836398363113, |
| "epoch": 0.0774818401937046, |
| "grad_norm": 0.4707717001438141, |
| "learning_rate": 2.1875e-05, |
| "loss": 1.8017537593841553, |
| "mean_token_accuracy": 0.5541446879506111, |
| "num_tokens": 778901.0, |
| "step": 8 |
| }, |
| { |
| "entropy": 2.0539309233427048, |
| "epoch": 0.08716707021791767, |
| "grad_norm": 0.5857245922088623, |
| "learning_rate": 2.5e-05, |
| "loss": 1.800880789756775, |
| "mean_token_accuracy": 0.5496064275503159, |
| "num_tokens": 875325.0, |
| "step": 9 |
| }, |
| { |
| "entropy": 1.9075840711593628, |
| "epoch": 0.09685230024213075, |
| "grad_norm": 0.5037109851837158, |
| "learning_rate": 2.8125000000000003e-05, |
| "loss": 1.673196792602539, |
| "mean_token_accuracy": 0.5737576559185982, |
| "num_tokens": 972839.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 1.860039845108986, |
| "epoch": 0.10653753026634383, |
| "grad_norm": 0.45144304633140564, |
| "learning_rate": 3.125e-05, |
| "loss": 1.6727261543273926, |
| "mean_token_accuracy": 0.5697960630059242, |
| "num_tokens": 1069150.0, |
| "step": 11 |
| }, |
| { |
| "entropy": 1.6962992250919342, |
| "epoch": 0.1162227602905569, |
| "grad_norm": 0.33423277735710144, |
| "learning_rate": 3.4375e-05, |
| "loss": 1.6035898923873901, |
| "mean_token_accuracy": 0.5795940384268761, |
| "num_tokens": 1166507.0, |
| "step": 12 |
| }, |
| { |
| "entropy": 1.5210626274347305, |
| "epoch": 0.12590799031476999, |
| "grad_norm": 0.2858195900917053, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 1.5204042196273804, |
| "mean_token_accuracy": 0.5941177308559418, |
| "num_tokens": 1264162.0, |
| "step": 13 |
| }, |
| { |
| "entropy": 1.5153919160366058, |
| "epoch": 0.13559322033898305, |
| "grad_norm": 0.30006346106529236, |
| "learning_rate": 4.0625000000000005e-05, |
| "loss": 1.565500259399414, |
| "mean_token_accuracy": 0.586014412343502, |
| "num_tokens": 1358318.0, |
| "step": 14 |
| }, |
| { |
| "entropy": 1.3367150872945786, |
| "epoch": 0.14527845036319612, |
| "grad_norm": 0.3114268481731415, |
| "learning_rate": 4.375e-05, |
| "loss": 1.430711030960083, |
| "mean_token_accuracy": 0.6141984984278679, |
| "num_tokens": 1455188.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 1.3922923356294632, |
| "epoch": 0.1549636803874092, |
| "grad_norm": 0.264522522687912, |
| "learning_rate": 4.6875e-05, |
| "loss": 1.460913896560669, |
| "mean_token_accuracy": 0.6049858629703522, |
| "num_tokens": 1553207.0, |
| "step": 16 |
| }, |
| { |
| "entropy": 1.388969361782074, |
| "epoch": 0.16464891041162227, |
| "grad_norm": 0.24329984188079834, |
| "learning_rate": 5e-05, |
| "loss": 1.4352588653564453, |
| "mean_token_accuracy": 0.6117960214614868, |
| "num_tokens": 1650103.0, |
| "step": 17 |
| }, |
| { |
| "entropy": 1.4225876778364182, |
| "epoch": 0.17433414043583534, |
| "grad_norm": 0.2702501714229584, |
| "learning_rate": 4.999859193643945e-05, |
| "loss": 1.40070378780365, |
| "mean_token_accuracy": 0.6150684952735901, |
| "num_tokens": 1746941.0, |
| "step": 18 |
| }, |
| { |
| "entropy": 1.4131463915109634, |
| "epoch": 0.18401937046004843, |
| "grad_norm": 0.25621092319488525, |
| "learning_rate": 4.999436790436924e-05, |
| "loss": 1.3876947164535522, |
| "mean_token_accuracy": 0.6200384646654129, |
| "num_tokens": 1844188.0, |
| "step": 19 |
| }, |
| { |
| "entropy": 1.4005486369132996, |
| "epoch": 0.1937046004842615, |
| "grad_norm": 0.2253018468618393, |
| "learning_rate": 4.9987328379605816e-05, |
| "loss": 1.3485538959503174, |
| "mean_token_accuracy": 0.6284598782658577, |
| "num_tokens": 1941380.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 1.4259228259325027, |
| "epoch": 0.2033898305084746, |
| "grad_norm": 0.21714746952056885, |
| "learning_rate": 4.9977474155117045e-05, |
| "loss": 1.3771286010742188, |
| "mean_token_accuracy": 0.621919259428978, |
| "num_tokens": 2039184.0, |
| "step": 21 |
| }, |
| { |
| "entropy": 1.3655668199062347, |
| "epoch": 0.21307506053268765, |
| "grad_norm": 0.24290618300437927, |
| "learning_rate": 4.9964806340932865e-05, |
| "loss": 1.3223435878753662, |
| "mean_token_accuracy": 0.631358377635479, |
| "num_tokens": 2136831.0, |
| "step": 22 |
| }, |
| { |
| "entropy": 1.337798997759819, |
| "epoch": 0.22276029055690072, |
| "grad_norm": 0.20359113812446594, |
| "learning_rate": 4.9949326364020314e-05, |
| "loss": 1.3159035444259644, |
| "mean_token_accuracy": 0.6321727335453033, |
| "num_tokens": 2233967.0, |
| "step": 23 |
| }, |
| { |
| "entropy": 1.2915576100349426, |
| "epoch": 0.2324455205811138, |
| "grad_norm": 0.18859286606311798, |
| "learning_rate": 4.993103596812268e-05, |
| "loss": 1.2781122922897339, |
| "mean_token_accuracy": 0.6395078897476196, |
| "num_tokens": 2331590.0, |
| "step": 24 |
| }, |
| { |
| "entropy": 1.3575056046247482, |
| "epoch": 0.24213075060532688, |
| "grad_norm": 0.17821626365184784, |
| "learning_rate": 4.9909937213563165e-05, |
| "loss": 1.3477147817611694, |
| "mean_token_accuracy": 0.6257509142160416, |
| "num_tokens": 2426793.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 1.2926480323076248, |
| "epoch": 0.25181598062953997, |
| "grad_norm": 0.19382886588573456, |
| "learning_rate": 4.988603247701277e-05, |
| "loss": 1.2814431190490723, |
| "mean_token_accuracy": 0.6403299421072006, |
| "num_tokens": 2523683.0, |
| "step": 26 |
| }, |
| { |
| "entropy": 1.2796363830566406, |
| "epoch": 0.26150121065375304, |
| "grad_norm": 0.20317526161670685, |
| "learning_rate": 4.985932445122257e-05, |
| "loss": 1.2663755416870117, |
| "mean_token_accuracy": 0.6411352977156639, |
| "num_tokens": 2620933.0, |
| "step": 27 |
| }, |
| { |
| "entropy": 1.2351761311292648, |
| "epoch": 0.2711864406779661, |
| "grad_norm": 0.17594024538993835, |
| "learning_rate": 4.982981614472039e-05, |
| "loss": 1.2373441457748413, |
| "mean_token_accuracy": 0.6497108340263367, |
| "num_tokens": 2717551.0, |
| "step": 28 |
| }, |
| { |
| "entropy": 1.2417249828577042, |
| "epoch": 0.28087167070217917, |
| "grad_norm": 0.16841042041778564, |
| "learning_rate": 4.979751088147192e-05, |
| "loss": 1.246107816696167, |
| "mean_token_accuracy": 0.6476121693849564, |
| "num_tokens": 2814604.0, |
| "step": 29 |
| }, |
| { |
| "entropy": 1.2138695567846298, |
| "epoch": 0.29055690072639223, |
| "grad_norm": 0.17539004981517792, |
| "learning_rate": 4.97624123005063e-05, |
| "loss": 1.2159419059753418, |
| "mean_token_accuracy": 0.6527048200368881, |
| "num_tokens": 2907459.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 1.2455604374408722, |
| "epoch": 0.30024213075060535, |
| "grad_norm": 0.1840510219335556, |
| "learning_rate": 4.972452435550614e-05, |
| "loss": 1.248232126235962, |
| "mean_token_accuracy": 0.6437666863203049, |
| "num_tokens": 3005431.0, |
| "step": 31 |
| }, |
| { |
| "entropy": 1.239659145474434, |
| "epoch": 0.3099273607748184, |
| "grad_norm": 0.1586979180574417, |
| "learning_rate": 4.968385131436222e-05, |
| "loss": 1.2250527143478394, |
| "mean_token_accuracy": 0.6520643010735512, |
| "num_tokens": 3102027.0, |
| "step": 32 |
| }, |
| { |
| "entropy": 1.235719233751297, |
| "epoch": 0.3196125907990315, |
| "grad_norm": 0.1657770574092865, |
| "learning_rate": 4.9640397758692715e-05, |
| "loss": 1.2115275859832764, |
| "mean_token_accuracy": 0.6527407914400101, |
| "num_tokens": 3199185.0, |
| "step": 33 |
| }, |
| { |
| "entropy": 1.2338766902685165, |
| "epoch": 0.32929782082324455, |
| "grad_norm": 0.1736833155155182, |
| "learning_rate": 4.9594168583327094e-05, |
| "loss": 1.1987342834472656, |
| "mean_token_accuracy": 0.6545186415314674, |
| "num_tokens": 3296154.0, |
| "step": 34 |
| }, |
| { |
| "entropy": 1.2545666545629501, |
| "epoch": 0.3389830508474576, |
| "grad_norm": 0.1628524214029312, |
| "learning_rate": 4.954516899575473e-05, |
| "loss": 1.229626178741455, |
| "mean_token_accuracy": 0.6491333171725273, |
| "num_tokens": 3393666.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 1.2120293527841568, |
| "epoch": 0.3486682808716707, |
| "grad_norm": 0.1564643383026123, |
| "learning_rate": 4.949340451553833e-05, |
| "loss": 1.2005155086517334, |
| "mean_token_accuracy": 0.6557489335536957, |
| "num_tokens": 3490912.0, |
| "step": 36 |
| }, |
| { |
| "entropy": 1.1949793994426727, |
| "epoch": 0.3583535108958838, |
| "grad_norm": 0.1508495956659317, |
| "learning_rate": 4.943888097369216e-05, |
| "loss": 1.1847431659698486, |
| "mean_token_accuracy": 0.6587688028812408, |
| "num_tokens": 3588393.0, |
| "step": 37 |
| }, |
| { |
| "entropy": 1.181449294090271, |
| "epoch": 0.36803874092009686, |
| "grad_norm": 0.16626174747943878, |
| "learning_rate": 4.938160451202521e-05, |
| "loss": 1.1869372129440308, |
| "mean_token_accuracy": 0.6568842083215714, |
| "num_tokens": 3685968.0, |
| "step": 38 |
| }, |
| { |
| "entropy": 1.1504246890544891, |
| "epoch": 0.37772397094430993, |
| "grad_norm": 0.15905380249023438, |
| "learning_rate": 4.9321581582449365e-05, |
| "loss": 1.1604914665222168, |
| "mean_token_accuracy": 0.6636896058917046, |
| "num_tokens": 3783418.0, |
| "step": 39 |
| }, |
| { |
| "entropy": 1.1543444991111755, |
| "epoch": 0.387409200968523, |
| "grad_norm": 0.15155690908432007, |
| "learning_rate": 4.9258818946252624e-05, |
| "loss": 1.152838110923767, |
| "mean_token_accuracy": 0.6673597618937492, |
| "num_tokens": 3881389.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 1.1898803561925888, |
| "epoch": 0.39709443099273606, |
| "grad_norm": 0.15378770232200623, |
| "learning_rate": 4.9193323673337476e-05, |
| "loss": 1.1838186979293823, |
| "mean_token_accuracy": 0.6584705263376236, |
| "num_tokens": 3978300.0, |
| "step": 41 |
| }, |
| { |
| "entropy": 1.178636059165001, |
| "epoch": 0.4067796610169492, |
| "grad_norm": 0.14911328256130219, |
| "learning_rate": 4.912510314142448e-05, |
| "loss": 1.1624752283096313, |
| "mean_token_accuracy": 0.6618187874555588, |
| "num_tokens": 4074320.0, |
| "step": 42 |
| }, |
| { |
| "entropy": 1.155859112739563, |
| "epoch": 0.41646489104116224, |
| "grad_norm": 0.14977990090847015, |
| "learning_rate": 4.9054165035221236e-05, |
| "loss": 1.1455484628677368, |
| "mean_token_accuracy": 0.6688502356410027, |
| "num_tokens": 4171931.0, |
| "step": 43 |
| }, |
| { |
| "entropy": 1.1802153587341309, |
| "epoch": 0.4261501210653753, |
| "grad_norm": 0.14762485027313232, |
| "learning_rate": 4.898051734555676e-05, |
| "loss": 1.1656816005706787, |
| "mean_token_accuracy": 0.6611011102795601, |
| "num_tokens": 4267550.0, |
| "step": 44 |
| }, |
| { |
| "entropy": 1.1514023691415787, |
| "epoch": 0.4358353510895884, |
| "grad_norm": 0.14387239515781403, |
| "learning_rate": 4.890416836848127e-05, |
| "loss": 1.1372427940368652, |
| "mean_token_accuracy": 0.6664102151989937, |
| "num_tokens": 4364712.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 1.156693086028099, |
| "epoch": 0.44552058111380144, |
| "grad_norm": 0.1518811285495758, |
| "learning_rate": 4.88251267043318e-05, |
| "loss": 1.1605509519577026, |
| "mean_token_accuracy": 0.6634868234395981, |
| "num_tokens": 4461394.0, |
| "step": 46 |
| }, |
| { |
| "entropy": 1.1185480505228043, |
| "epoch": 0.4552058111380145, |
| "grad_norm": 0.16213111579418182, |
| "learning_rate": 4.87434012567633e-05, |
| "loss": 1.1149487495422363, |
| "mean_token_accuracy": 0.6748593971133232, |
| "num_tokens": 4558878.0, |
| "step": 47 |
| }, |
| { |
| "entropy": 1.1710628867149353, |
| "epoch": 0.4648910411622276, |
| "grad_norm": 0.14876942336559296, |
| "learning_rate": 4.865900123174574e-05, |
| "loss": 1.15852952003479, |
| "mean_token_accuracy": 0.6628599911928177, |
| "num_tokens": 4656033.0, |
| "step": 48 |
| }, |
| { |
| "entropy": 1.184880554676056, |
| "epoch": 0.4745762711864407, |
| "grad_norm": 0.14967085421085358, |
| "learning_rate": 4.857193613652711e-05, |
| "loss": 1.1690523624420166, |
| "mean_token_accuracy": 0.662392869591713, |
| "num_tokens": 4753610.0, |
| "step": 49 |
| }, |
| { |
| "entropy": 1.17043799161911, |
| "epoch": 0.48426150121065376, |
| "grad_norm": 0.156271830201149, |
| "learning_rate": 4.848221577856243e-05, |
| "loss": 1.1510560512542725, |
| "mean_token_accuracy": 0.6638557314872742, |
| "num_tokens": 4851486.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 1.1305849254131317, |
| "epoch": 0.4939467312348668, |
| "grad_norm": 0.14663065969944, |
| "learning_rate": 4.838985026440905e-05, |
| "loss": 1.112675428390503, |
| "mean_token_accuracy": 0.6735092177987099, |
| "num_tokens": 4948781.0, |
| "step": 51 |
| }, |
| { |
| "entropy": 1.1443408280611038, |
| "epoch": 0.5036319612590799, |
| "grad_norm": 0.14738105237483978, |
| "learning_rate": 4.829484999858815e-05, |
| "loss": 1.13261878490448, |
| "mean_token_accuracy": 0.6675093844532967, |
| "num_tokens": 5046085.0, |
| "step": 52 |
| }, |
| { |
| "entropy": 1.1511103957891464, |
| "epoch": 0.513317191283293, |
| "grad_norm": 0.15696625411510468, |
| "learning_rate": 4.819722568241274e-05, |
| "loss": 1.1610808372497559, |
| "mean_token_accuracy": 0.6629386246204376, |
| "num_tokens": 5142470.0, |
| "step": 53 |
| }, |
| { |
| "entropy": 1.13540880382061, |
| "epoch": 0.5230024213075061, |
| "grad_norm": 0.14982947707176208, |
| "learning_rate": 4.8096988312782174e-05, |
| "loss": 1.1378846168518066, |
| "mean_token_accuracy": 0.666424423456192, |
| "num_tokens": 5240348.0, |
| "step": 54 |
| }, |
| { |
| "entropy": 1.1485055983066559, |
| "epoch": 0.5326876513317191, |
| "grad_norm": 0.15001113712787628, |
| "learning_rate": 4.799414918094347e-05, |
| "loss": 1.1458028554916382, |
| "mean_token_accuracy": 0.6636912375688553, |
| "num_tokens": 5337856.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 1.1504357308149338, |
| "epoch": 0.5423728813559322, |
| "grad_norm": 0.1556474268436432, |
| "learning_rate": 4.788871987121937e-05, |
| "loss": 1.135033369064331, |
| "mean_token_accuracy": 0.6674922555685043, |
| "num_tokens": 5435150.0, |
| "step": 56 |
| }, |
| { |
| "entropy": 1.1426950842142105, |
| "epoch": 0.5520581113801453, |
| "grad_norm": 0.147213876247406, |
| "learning_rate": 4.77807122597034e-05, |
| "loss": 1.1313400268554688, |
| "mean_token_accuracy": 0.6694349721074104, |
| "num_tokens": 5533227.0, |
| "step": 57 |
| }, |
| { |
| "entropy": 1.1269017159938812, |
| "epoch": 0.5617433414043583, |
| "grad_norm": 0.15351133048534393, |
| "learning_rate": 4.767013851292212e-05, |
| "loss": 1.1154887676239014, |
| "mean_token_accuracy": 0.6716312021017075, |
| "num_tokens": 5630374.0, |
| "step": 58 |
| }, |
| { |
| "entropy": 1.1352972239255905, |
| "epoch": 0.5714285714285714, |
| "grad_norm": 0.1449081301689148, |
| "learning_rate": 4.755701108646463e-05, |
| "loss": 1.115692377090454, |
| "mean_token_accuracy": 0.6710918322205544, |
| "num_tokens": 5727367.0, |
| "step": 59 |
| }, |
| { |
| "entropy": 1.134296178817749, |
| "epoch": 0.5811138014527845, |
| "grad_norm": 0.153062105178833, |
| "learning_rate": 4.744134272357948e-05, |
| "loss": 1.1301031112670898, |
| "mean_token_accuracy": 0.6712843775749207, |
| "num_tokens": 5824218.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 1.1202774196863174, |
| "epoch": 0.5907990314769975, |
| "grad_norm": 0.14879855513572693, |
| "learning_rate": 4.732314645373921e-05, |
| "loss": 1.1113876104354858, |
| "mean_token_accuracy": 0.6735736131668091, |
| "num_tokens": 5921571.0, |
| "step": 61 |
| }, |
| { |
| "entropy": 1.102357640862465, |
| "epoch": 0.6004842615012107, |
| "grad_norm": 0.15212750434875488, |
| "learning_rate": 4.7202435591172676e-05, |
| "loss": 1.0985870361328125, |
| "mean_token_accuracy": 0.675997368991375, |
| "num_tokens": 6018773.0, |
| "step": 62 |
| }, |
| { |
| "entropy": 1.1048029512166977, |
| "epoch": 0.6101694915254238, |
| "grad_norm": 0.14792507886886597, |
| "learning_rate": 4.7079223733365237e-05, |
| "loss": 1.095569372177124, |
| "mean_token_accuracy": 0.675012968480587, |
| "num_tokens": 6115912.0, |
| "step": 63 |
| }, |
| { |
| "entropy": 1.1288667768239975, |
| "epoch": 0.6198547215496368, |
| "grad_norm": 0.14735190570354462, |
| "learning_rate": 4.6953524759527054e-05, |
| "loss": 1.11784827709198, |
| "mean_token_accuracy": 0.6701762154698372, |
| "num_tokens": 6212536.0, |
| "step": 64 |
| }, |
| { |
| "entropy": 1.114186018705368, |
| "epoch": 0.6295399515738499, |
| "grad_norm": 0.15394103527069092, |
| "learning_rate": 4.6825352829029705e-05, |
| "loss": 1.1040326356887817, |
| "mean_token_accuracy": 0.6742865368723869, |
| "num_tokens": 6310026.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 1.0817014202475548, |
| "epoch": 0.639225181598063, |
| "grad_norm": 0.1501314491033554, |
| "learning_rate": 4.6694722379811185e-05, |
| "loss": 1.08419930934906, |
| "mean_token_accuracy": 0.6813223287463188, |
| "num_tokens": 6405142.0, |
| "step": 66 |
| }, |
| { |
| "entropy": 1.1135721951723099, |
| "epoch": 0.648910411622276, |
| "grad_norm": 0.16784843802452087, |
| "learning_rate": 4.656164812674951e-05, |
| "loss": 1.1132102012634277, |
| "mean_token_accuracy": 0.6742275431752205, |
| "num_tokens": 6502523.0, |
| "step": 67 |
| }, |
| { |
| "entropy": 1.1133443415164948, |
| "epoch": 0.6585956416464891, |
| "grad_norm": 0.15567201375961304, |
| "learning_rate": 4.642614506000523e-05, |
| "loss": 1.1113190650939941, |
| "mean_token_accuracy": 0.6731716245412827, |
| "num_tokens": 6599085.0, |
| "step": 68 |
| }, |
| { |
| "entropy": 1.091795675456524, |
| "epoch": 0.6682808716707022, |
| "grad_norm": 0.14981144666671753, |
| "learning_rate": 4.628822844333278e-05, |
| "loss": 1.0913615226745605, |
| "mean_token_accuracy": 0.6778776124119759, |
| "num_tokens": 6696224.0, |
| "step": 69 |
| }, |
| { |
| "entropy": 1.0920320302248, |
| "epoch": 0.6779661016949152, |
| "grad_norm": 0.15485303103923798, |
| "learning_rate": 4.614791381236115e-05, |
| "loss": 1.0870628356933594, |
| "mean_token_accuracy": 0.6780931428074837, |
| "num_tokens": 6792189.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 1.1014160960912704, |
| "epoch": 0.6876513317191283, |
| "grad_norm": 0.1586335003376007, |
| "learning_rate": 4.6005216972843864e-05, |
| "loss": 1.1016792058944702, |
| "mean_token_accuracy": 0.6750583723187447, |
| "num_tokens": 6889269.0, |
| "step": 71 |
| }, |
| { |
| "entropy": 1.095201924443245, |
| "epoch": 0.6973365617433414, |
| "grad_norm": 0.15514244139194489, |
| "learning_rate": 4.5860153998878494e-05, |
| "loss": 1.089525580406189, |
| "mean_token_accuracy": 0.6761212572455406, |
| "num_tokens": 6987001.0, |
| "step": 72 |
| }, |
| { |
| "entropy": 1.110721379518509, |
| "epoch": 0.7070217917675545, |
| "grad_norm": 0.15483509004116058, |
| "learning_rate": 4.571274123109606e-05, |
| "loss": 1.1064794063568115, |
| "mean_token_accuracy": 0.6743339449167252, |
| "num_tokens": 7083766.0, |
| "step": 73 |
| }, |
| { |
| "entropy": 1.1040757596492767, |
| "epoch": 0.7167070217917676, |
| "grad_norm": 0.1559927612543106, |
| "learning_rate": 4.5562995274820284e-05, |
| "loss": 1.082243800163269, |
| "mean_token_accuracy": 0.6789897233247757, |
| "num_tokens": 7179679.0, |
| "step": 74 |
| }, |
| { |
| "entropy": 1.1098376661539078, |
| "epoch": 0.7263922518159807, |
| "grad_norm": 0.15505605936050415, |
| "learning_rate": 4.541093299819714e-05, |
| "loss": 1.0888028144836426, |
| "mean_token_accuracy": 0.6794665902853012, |
| "num_tokens": 7276243.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 1.099312648177147, |
| "epoch": 0.7360774818401937, |
| "grad_norm": 0.14871232211589813, |
| "learning_rate": 4.5256571530294664e-05, |
| "loss": 1.0875135660171509, |
| "mean_token_accuracy": 0.6783665344119072, |
| "num_tokens": 7373015.0, |
| "step": 76 |
| }, |
| { |
| "entropy": 1.0749460384249687, |
| "epoch": 0.7457627118644068, |
| "grad_norm": 0.17334473133087158, |
| "learning_rate": 4.5099928259173516e-05, |
| "loss": 1.0605744123458862, |
| "mean_token_accuracy": 0.6834923177957535, |
| "num_tokens": 7469189.0, |
| "step": 77 |
| }, |
| { |
| "entropy": 1.0772480070590973, |
| "epoch": 0.7554479418886199, |
| "grad_norm": 0.15214787423610687, |
| "learning_rate": 4.4941020829928245e-05, |
| "loss": 1.076210856437683, |
| "mean_token_accuracy": 0.6795796528458595, |
| "num_tokens": 7565874.0, |
| "step": 78 |
| }, |
| { |
| "entropy": 1.0568204671144485, |
| "epoch": 0.7651331719128329, |
| "grad_norm": 0.15063218772411346, |
| "learning_rate": 4.477986714269972e-05, |
| "loss": 1.060287356376648, |
| "mean_token_accuracy": 0.6827899366617203, |
| "num_tokens": 7662843.0, |
| "step": 79 |
| }, |
| { |
| "entropy": 1.084660217165947, |
| "epoch": 0.774818401937046, |
| "grad_norm": 0.15119187533855438, |
| "learning_rate": 4.4616485350658685e-05, |
| "loss": 1.091611385345459, |
| "mean_token_accuracy": 0.6798556670546532, |
| "num_tokens": 7759463.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 1.1101327538490295, |
| "epoch": 0.784503631961259, |
| "grad_norm": 0.15529696643352509, |
| "learning_rate": 4.445089385796099e-05, |
| "loss": 1.1128976345062256, |
| "mean_token_accuracy": 0.6707641705870628, |
| "num_tokens": 7857012.0, |
| "step": 81 |
| }, |
| { |
| "entropy": 1.091973900794983, |
| "epoch": 0.7941888619854721, |
| "grad_norm": 0.1531902551651001, |
| "learning_rate": 4.4283111317674374e-05, |
| "loss": 1.090956687927246, |
| "mean_token_accuracy": 0.6741223037242889, |
| "num_tokens": 7954176.0, |
| "step": 82 |
| }, |
| { |
| "entropy": 1.0863638073205948, |
| "epoch": 0.8038740920096852, |
| "grad_norm": 0.1566418707370758, |
| "learning_rate": 4.4113156629677316e-05, |
| "loss": 1.0832655429840088, |
| "mean_token_accuracy": 0.678005263209343, |
| "num_tokens": 8051738.0, |
| "step": 83 |
| }, |
| { |
| "entropy": 1.061260737478733, |
| "epoch": 0.8135593220338984, |
| "grad_norm": 0.15304933488368988, |
| "learning_rate": 4.394104893853007e-05, |
| "loss": 1.0538866519927979, |
| "mean_token_accuracy": 0.6874052137136459, |
| "num_tokens": 8148640.0, |
| "step": 84 |
| }, |
| { |
| "entropy": 1.0719867199659348, |
| "epoch": 0.8232445520581114, |
| "grad_norm": 0.1544543355703354, |
| "learning_rate": 4.3766807631318106e-05, |
| "loss": 1.0574662685394287, |
| "mean_token_accuracy": 0.6843332424759865, |
| "num_tokens": 8245229.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 1.0613527670502663, |
| "epoch": 0.8329297820823245, |
| "grad_norm": 0.14801454544067383, |
| "learning_rate": 4.359045233546827e-05, |
| "loss": 1.0512840747833252, |
| "mean_token_accuracy": 0.6862121224403381, |
| "num_tokens": 8341261.0, |
| "step": 86 |
| }, |
| { |
| "entropy": 1.0908231735229492, |
| "epoch": 0.8426150121065376, |
| "grad_norm": 0.15294907987117767, |
| "learning_rate": 4.341200291653781e-05, |
| "loss": 1.0715211629867554, |
| "mean_token_accuracy": 0.6817414835095406, |
| "num_tokens": 8438977.0, |
| "step": 87 |
| }, |
| { |
| "entropy": 1.0881828963756561, |
| "epoch": 0.8523002421307506, |
| "grad_norm": 0.15974564850330353, |
| "learning_rate": 4.323147947597666e-05, |
| "loss": 1.0726957321166992, |
| "mean_token_accuracy": 0.6810331121087074, |
| "num_tokens": 8536075.0, |
| "step": 88 |
| }, |
| { |
| "entropy": 1.0424850583076477, |
| "epoch": 0.8619854721549637, |
| "grad_norm": 0.1496453583240509, |
| "learning_rate": 4.3048902348863116e-05, |
| "loss": 1.0368857383728027, |
| "mean_token_accuracy": 0.6897075176239014, |
| "num_tokens": 8633706.0, |
| "step": 89 |
| }, |
| { |
| "entropy": 1.0516717359423637, |
| "epoch": 0.8716707021791767, |
| "grad_norm": 0.15799377858638763, |
| "learning_rate": 4.2864292101613136e-05, |
| "loss": 1.0576695203781128, |
| "mean_token_accuracy": 0.6859739124774933, |
| "num_tokens": 8731736.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 1.0575535222887993, |
| "epoch": 0.8813559322033898, |
| "grad_norm": 0.15401387214660645, |
| "learning_rate": 4.267766952966369e-05, |
| "loss": 1.0623745918273926, |
| "mean_token_accuracy": 0.6833577901124954, |
| "num_tokens": 8829732.0, |
| "step": 91 |
| }, |
| { |
| "entropy": 1.0572301000356674, |
| "epoch": 0.8910411622276029, |
| "grad_norm": 0.15554137527942657, |
| "learning_rate": 4.248905565513023e-05, |
| "loss": 1.0531975030899048, |
| "mean_token_accuracy": 0.6840359568595886, |
| "num_tokens": 8927532.0, |
| "step": 92 |
| }, |
| { |
| "entropy": 1.047728806734085, |
| "epoch": 0.9007263922518159, |
| "grad_norm": 0.15111669898033142, |
| "learning_rate": 4.229847172443866e-05, |
| "loss": 1.0404102802276611, |
| "mean_token_accuracy": 0.6903342977166176, |
| "num_tokens": 9023586.0, |
| "step": 93 |
| }, |
| { |
| "entropy": 1.0721349269151688, |
| "epoch": 0.910411622276029, |
| "grad_norm": 0.1501697152853012, |
| "learning_rate": 4.210593920593201e-05, |
| "loss": 1.0653115510940552, |
| "mean_token_accuracy": 0.6849683672189713, |
| "num_tokens": 9121309.0, |
| "step": 94 |
| }, |
| { |
| "entropy": 1.0481175184249878, |
| "epoch": 0.9200968523002422, |
| "grad_norm": 0.15556755661964417, |
| "learning_rate": 4.191147978745218e-05, |
| "loss": 1.0338795185089111, |
| "mean_token_accuracy": 0.6906152591109276, |
| "num_tokens": 9218589.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 1.0750476568937302, |
| "epoch": 0.9297820823244553, |
| "grad_norm": 0.1613941788673401, |
| "learning_rate": 4.171511537389684e-05, |
| "loss": 1.067610502243042, |
| "mean_token_accuracy": 0.6825880706310272, |
| "num_tokens": 9315388.0, |
| "step": 96 |
| }, |
| { |
| "entropy": 1.0497909039258957, |
| "epoch": 0.9394673123486683, |
| "grad_norm": 0.15890054404735565, |
| "learning_rate": 4.151686808475204e-05, |
| "loss": 1.0334787368774414, |
| "mean_token_accuracy": 0.6903782784938812, |
| "num_tokens": 9412518.0, |
| "step": 97 |
| }, |
| { |
| "entropy": 1.062135674059391, |
| "epoch": 0.9491525423728814, |
| "grad_norm": 0.15434817969799042, |
| "learning_rate": 4.131676025160047e-05, |
| "loss": 1.0537683963775635, |
| "mean_token_accuracy": 0.6860457882285118, |
| "num_tokens": 9509730.0, |
| "step": 98 |
| }, |
| { |
| "entropy": 1.0554313883185387, |
| "epoch": 0.9588377723970944, |
| "grad_norm": 0.1582096815109253, |
| "learning_rate": 4.111481441560598e-05, |
| "loss": 1.050376296043396, |
| "mean_token_accuracy": 0.6866516023874283, |
| "num_tokens": 9607061.0, |
| "step": 99 |
| }, |
| { |
| "entropy": 1.0587477162480354, |
| "epoch": 0.9685230024213075, |
| "grad_norm": 0.15938952565193176, |
| "learning_rate": 4.091105332497439e-05, |
| "loss": 1.0483958721160889, |
| "mean_token_accuracy": 0.6882701963186264, |
| "num_tokens": 9703922.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 1.0580755025148392, |
| "epoch": 0.9782082324455206, |
| "grad_norm": 0.15547914803028107, |
| "learning_rate": 4.070549993239106e-05, |
| "loss": 1.046097993850708, |
| "mean_token_accuracy": 0.6853689402341843, |
| "num_tokens": 9801726.0, |
| "step": 101 |
| }, |
| { |
| "entropy": 1.0280383378267288, |
| "epoch": 0.9878934624697336, |
| "grad_norm": 0.1550140529870987, |
| "learning_rate": 4.049817739243532e-05, |
| "loss": 1.0170772075653076, |
| "mean_token_accuracy": 0.6949135884642601, |
| "num_tokens": 9898921.0, |
| "step": 102 |
| }, |
| { |
| "entropy": 1.0521605014801025, |
| "epoch": 0.9975786924939467, |
| "grad_norm": 0.17861391603946686, |
| "learning_rate": 4.028910905897229e-05, |
| "loss": 1.0528624057769775, |
| "mean_token_accuracy": 0.6859815418720245, |
| "num_tokens": 9993769.0, |
| "step": 103 |
| }, |
| { |
| "entropy": 1.078683614730835, |
| "epoch": 1.0, |
| "grad_norm": 0.293241411447525, |
| "learning_rate": 4.007831848252211e-05, |
| "loss": 1.0659458637237549, |
| "mean_token_accuracy": 0.6819257438182831, |
| "num_tokens": 10018344.0, |
| "step": 104 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 312, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.4092280526882734e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
